Graph WaveNet for Deep Spatial-Temporal Graph Modeling

Abstract

Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.

to be published in IJCAI-2019

References in corpus (6)

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Neural Message Passing for Quantum Chemistry
• Learning Graph Embedding with Adversarial Training Methods
• Neural Machine Translation in Linear Time
• Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
• GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs

Cited by in corpus (10)

• Graph Neural Network for Traffic Forecasting: A Survey
• Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• ETA Prediction with Graph Neural Networks in Google Maps
• Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting
• Sparse Transformer with Local and Seasonal Adaptation for Multivariate Time Series Forecasting
• Deep Multi-View Spatiotemporal Virtual Graph Neural Network for Significant Citywide Ride-hailing Demand Prediction
• Network Level Spatial Temporal Traffic State Forecasting with Hierarchical-Attention-LSTM (HierAttnLSTM)
• Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction
• A Graph Convolutional Network with Signal Phasing Information for Arterial Traffic Prediction